Publications
See the full publication list on my Google Scholar.
* indicates equal contribution.
Preprint
- Preprint 2026Self-Evolving Defense: Continual Security Policy Learning for LLM Agents
Conference
2026
- NeurIPS 2026The Last Human-Written Paper: Agent-Native Research Artifacts
- EMNLP 2026CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents
- EMNLP 2026(Findings) Beyond Confidence: Test-Time Scaling for Multi-Turn Search Agents via Retrieval Grounding
- ICML 2026XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation
- ICLR 2026OPPO: Accelerating PPO-based RLHF via Pipeline Overlap
- CHI 2026EchoScriptor: Automatic Lifelogging Narratives via Activity-Based Audio–Language Model
- ASPLOS 2026WAVE: Leveraging Architecture Observation for Privacy-Preserving Model Oversight
2025
- COLM 2025Plato: Plan to Efficiently Decode for Large Language Model Inference
- ICLR 2025ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
- WWW 2025Harmful Terms and Where to Find Them: Measuring and Modeling Unfavorable Financial Terms and Conditions in Shopping Websites at ScaleOral
2024
- NeurIPS 2024
- ECCV 2024Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation
- ICLR 2024CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
2023
2020
2018
- NDSS 2018Smoke Screener or Straight Shooter: Detecting Elite Sybil Attacks in User-Review Social Networks